Some cool images of “masks” generated by a BigGAN model using a high truncation threshold which lets us control the variety of the images. They were generated on this demo page, with a model that was already trained for me. The paper introducing the truncation threshold (or truncation trick) is “Large Scale GAN Training for High Fidelity Natural Image Synthesis” by Andrew Brock, Jeff Donahue, and Karen Simonyan. You can see some weak cases of class leakage (especially some animal features) in these images due to the high truncation threshold. These images are cherrypicked (to look cool) and not a representation of the generator’s real distribution. The truncation threshold used was around 0.6-1.0.